# Embodify MCP server

> Lets AI agents observe and control simulated or real robots through MCP-compatible tools and skills.

- Repository: https://github.com/YidaYang/embodify
- Page: https://hostedmcp.org/servers/yidayang/embodify
- Transport: stdio
- Stars: 5
- License: Apache-2.0
- Latest version: 0.1.0a2

## Install

### Claude Code

```sh
claude mcp add embodify -- uvx embodify-mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "embodify": {
      "command": "uvx",
      "args": [
        "embodify-mcp"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "embodify": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "embodify-mcp"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"embodify","type":"stdio","command":"uvx","args":["embodify-mcp"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "embodify": {
      "command": "uvx",
      "args": [
        "embodify-mcp"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add embodify -- uvx embodify-mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.embodify]
command = "uvx"
args = ["embodify-mcp"]
```

### Gemini CLI

```sh
gemini mcp add -s user embodify uvx -- embodify-mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "embodify": {
      "command": "uvx",
      "args": [
        "embodify-mcp"
      ]
    }
  }
}
```

## Tools (8)

- `get_session_info`
- `list_tasks`
- `reset_task`
- `observe`
- `move_relative`
- `set_gripper`
- `control_arms`
- `stop_episode`

## FAQ

### What robot simulators are supported?

Currently, it supports LIBERO and RoboDojo, with RoboTwin coming soon.

### Can I run the simulator on a remote machine?

Yes, you can run the simulator on a GPU server via SSH or trusted TCP while keeping the agent on your local machine.

### How can I monitor the robot's actions?

You can watch running episodes live in a browser or replay past ones frame by frame by enabling the monitor port in the configuration.

### Does it work with existing AI agents?

Yes, it works with any MCP-capable agent like Claude Code or Codex.
